Chapter 5 Community composition

load("data/data.Rdata")

5.1 Taxonomy overview

5.1.1 Stacked barplot

genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  filter(count > 0) %>% #filter 0 counts
  ggplot(., aes(x=sample,y=count, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors) +
    facet_nested(. ~ altitude + treatment,  scales="free") + #facet per day and treatment
    guides(fill = guide_legend(ncol = 1)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black")) +
   labs(fill="Phylum",y = "Relative abundance",x="Samples")

Number of bacteria phyla

[1] 13

5.1.2 Phylum relative abundances

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample,phylum,region, environment,treatment) %>%
  summarise(relabun=sum(count))

phylum_summary %>%
    group_by(phylum) %>%
    summarise(total_mean=mean(relabun*100, na.rm=T),
              total_sd=sd(relabun*100, na.rm=T))  %>%
    mutate(total=str_c(round(total_mean,2),"±",round(total_sd,2))) %>% 
    arrange(-total_mean) %>% 
    dplyr::select(phylum,total) %>% 
    tt()

phylum	total
p__Bacteroidota	56.02±16.86
p__Bacillota_A	17.72±6.39
p__Pseudomonadota	11.57±13.5
p__Bacillota	5.48±8.81
p__Verrucomicrobiota	4.12±4.51
p__Desulfobacterota	1.79±1.74
p__Fusobacteriota	1.37±2.18
p__Bacillota_C	0.65±0.93
p__Deferribacterota	0.6±0.77
p__Cyanobacteriota	0.37±0.5
p__Bacillota_B	0.15±0.14
p__Elusimicrobiota	0.13±0.43
p__Chlamydiota	0.03±0.08

phylum_arrange <- phylum_summary %>%
    group_by(phylum) %>%
    summarise(mean=mean(relabun)) %>%
    arrange(-mean) %>%
    select(phylum) %>%
    pull()

phylum_summary %>%
    filter(phylum %in% phylum_arrange) %>%
    mutate(phylum=factor(phylum,levels=rev(phylum_arrange))) %>%
    ggplot(aes(x=relabun, y=phylum, group=phylum, color=phylum)) +
        scale_color_manual(values=phylum_colors[rev(phylum_arrange)]) +
        geom_jitter(alpha=0.5) + 
        theme_minimal() + 
        theme(legend.position="none") +
        labs(y="Phylum",x="Relative abundance")

5.2 Taxonomy boxplot

5.2.1 Family

family_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,family) %>%
  summarise(relabun=sum(count))

family_summary %>%
    group_by(family) %>%
    summarise(mean=mean(relabun, na.rm=T),sd=sd(relabun, na.rm=T)) %>%
    arrange(-mean) %>%
    tt()

family	mean	sd
f__Bacteroidaceae	2.747168e-01	1.407196e-01
f__Rikenellaceae	1.391991e-01	7.396770e-02
f__Tannerellaceae	7.720647e-02	4.561100e-02
f__Ruminococcaceae	5.793749e-02	4.189494e-02
f__Lachnospiraceae	4.729335e-02	3.337791e-02
f__Enterobacteriaceae	4.336104e-02	9.482159e-02
f__Akkermansiaceae	3.968436e-02	4.368196e-02
f__Marinifilaceae	3.738796e-02	3.555050e-02
f__Aeromonadaceae	3.216280e-02	5.116161e-02
f__Mycoplasmoidaceae	3.122255e-02	8.895328e-02
f__Erysipelotrichaceae	2.221957e-02	1.788968e-02
f__	1.956762e-02	1.924658e-02
f__Desulfovibrionaceae	1.794839e-02	1.740772e-02
f__Fusobacteriaceae	1.368885e-02	2.180794e-02
f__Clostridiaceae	1.366840e-02	1.906657e-02
f__Moraxellaceae	1.342615e-02	2.724203e-02
f__Oscillospiraceae	1.250406e-02	8.936335e-03
f__Cellulosilyticaceae	1.133545e-02	2.080456e-02
f__Butyricicoccaceae	9.655203e-03	2.753799e-02
f__CAG-239	8.744086e-03	1.388356e-02
f__CHK158-818	7.109525e-03	8.651652e-03
f__Anaerovoracaceae	6.170476e-03	9.224529e-03
f__Mucispirillaceae	6.016547e-03	7.689861e-03
f__Peptostreptococcaceae	5.928800e-03	1.660295e-02
f__P3	5.211451e-03	8.758697e-03
f__Muribaculaceae	5.091676e-03	6.107022e-03
f__UBA3637	5.049775e-03	1.024626e-02
f__Gastranaerophilaceae	3.475214e-03	4.812600e-03
f__Anaerotignaceae	2.499790e-03	2.422026e-03
f__UBA932	2.488889e-03	4.069053e-03
f__Acutalibacteraceae	2.311710e-03	3.337834e-03
f__Chromobacteriaceae	2.083279e-03	9.013217e-03
f__UBA3830	2.074625e-03	3.362372e-03
f__Pumilibacteraceae	2.041528e-03	2.464352e-03
f__Massilibacillaceae	1.915668e-03	3.861941e-03
f__Succinispiraceae	1.875117e-03	2.130021e-03
f__UBA1997	1.620725e-03	4.440974e-03
f__Chitinibacteraceae	1.502709e-03	3.412014e-03
f__Pseudomonadaceae	1.420060e-03	2.808340e-03
f__Peptococcaceae	1.264453e-03	1.169734e-03
f__Elusimicrobiaceae	1.261359e-03	4.278766e-03
f__Burkholderiaceae_A	9.378374e-04	2.509149e-03
f__CAG-508	9.213532e-04	4.996540e-03
f__Coprobacteraceae	9.079215e-04	1.527339e-03
f__Shewanellaceae	8.297368e-04	2.690699e-03
f__Coprobacillaceae	7.318328e-04	1.542562e-03
f__Sedimentibacteraceae	6.927406e-04	1.016728e-03
f__Xanthobacteraceae	6.440180e-04	2.407832e-03
f__UBA1820	5.396558e-04	9.137754e-04
f__GCF-1484045	4.480219e-04	2.494481e-03
f__CALVMC01	3.833973e-04	1.889124e-03
f__Chlamydiaceae	3.250519e-04	8.432063e-04
f__Borkfalkiaceae	3.144307e-04	5.804720e-04
f__UBA7702	2.807538e-04	6.721141e-04
f__Eubacteriaceae	2.693395e-04	4.861755e-04
f__UBA3700	1.657496e-04	9.228548e-04
f__CALYAR01	1.366137e-04	2.325915e-04
f__Enterococcaceae	1.029579e-04	5.732451e-04
f__UBA660	2.552412e-05	7.936623e-05

family_arrange <- family_summary %>%
    group_by(family) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(family) %>%
    pull()

# Per origin
family_summary %>%
    left_join(genome_metadata %>% select(family,phylum) %>% unique(),by=join_by(family==family)) %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    filter(family %in% family_arrange[1:20]) %>%
    mutate(family=factor(family,levels=rev(family_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=family, group=family, color=phylum)) +
        scale_color_manual(values=phylum_colors[-8]) +
        geom_jitter(alpha=0.5) + 
        facet_grid(.~environment)+
        theme_minimal() + 
        labs(y="Family", x="Relative abundance", color="Phylum")

5.2.2 Genus

genus_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,phylum,genus) %>%
  summarise(relabun=sum(count)) %>%
  filter(genus != "g__") %>%
  mutate(genus= sub("^g__", "", genus))

genus_summary_sort <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=mean(relabun, na.rm=T),sd=sd(relabun, na.rm=T)) %>%
    arrange(-mean) 

genus_summary_sort %>%
    tt()

genus	mean	sd
Bacteroides	2.676340e-01	1.399196e-01
Parabacteroides	6.376349e-02	3.960345e-02
Mucinivorans	6.085416e-02	4.344629e-02
Aeromonas	3.216280e-02	5.116161e-02
Mycoplasma_L	2.602922e-02	8.972179e-02
Akkermansia	2.440550e-02	3.614255e-02
Odoribacter	2.389115e-02	2.235810e-02
JADFUS01	2.216792e-02	1.316718e-02
Hafnia	1.922885e-02	9.188555e-02
UBA866	1.817084e-02	2.179441e-02
Alistipes	1.625622e-02	1.344232e-02
Plesiomonas	1.460621e-02	3.266225e-02
Parabacteroides_B	1.344298e-02	1.263954e-02
Acinetobacter	1.342615e-02	2.724203e-02
Cetobacterium	1.241520e-02	2.123151e-02
Dielma	1.189375e-02	1.483388e-02
Clostridium	1.178483e-02	1.804656e-02
14-2	9.530791e-03	2.077519e-02
Bilophila	9.443387e-03	1.270499e-02
CAJGBR01	9.261016e-03	8.562777e-03
Angelakisella	7.718052e-03	7.686128e-03
Clostridium_Q	7.535231e-03	8.628377e-03
JAIHAL01	7.428449e-03	1.475536e-02
Gallibacteroides	7.109525e-03	8.651652e-03
Bacteroides_G	5.906571e-03	6.736493e-03
Hydrogenoanaerobacterium	5.795122e-03	6.095362e-03
Buttiauxella	5.526548e-03	1.517479e-02
SZUA-378	5.304805e-03	1.559558e-02
Malacoplasma	5.193336e-03	1.101657e-02
HGM05232	5.091676e-03	6.107022e-03
Hungatella_A	4.823985e-03	5.525123e-03
Anaerotruncus	4.430928e-03	4.607282e-03
Pseudoflavonifractor	3.911764e-03	4.052227e-03
Alistipes_A	3.867619e-03	3.658744e-03
Intestinimonas	3.801876e-03	3.660942e-03
Tidjanibacter	3.641420e-03	3.113585e-03
Anaerovorax	3.457110e-03	7.930141e-03
Anaerorhabdus	3.342681e-03	4.665953e-03
Paraclostridium	3.303535e-03	1.632282e-02
Gallalistipes	2.764951e-03	2.526439e-03
Avirikenella	2.703337e-03	4.073629e-03
Mobilisporobacter	2.643797e-03	4.233095e-03
UMGS1251	2.623868e-03	4.428322e-03
RGIG3102	2.550546e-03	4.796159e-03
Egerieousia	2.488889e-03	4.069053e-03
JAGAJR01	2.433883e-03	5.478338e-03
Craterilacuibacter	2.083279e-03	9.013217e-03
Copranaerobaculum	2.066120e-03	8.740585e-03
UMGS1202	1.928935e-03	2.061976e-03
Sarcina	1.883573e-03	3.313599e-03
JAAYQI01	1.821441e-03	2.177416e-03
Amedibacillus	1.771861e-03	2.511258e-03
JAHHTP01	1.702809e-03	2.122800e-03
Rikenella	1.556573e-03	2.583114e-03
Romboutsia_D	1.554865e-03	3.682587e-03
Evtepia	1.531626e-03	1.774639e-03
Ruthenibacterium	1.530835e-03	2.751232e-03
Deefgea	1.502709e-03	3.412014e-03
Intestinibacillus	1.498170e-03	1.772211e-03
Budvicia	1.431037e-03	6.773380e-03
Butyricimonas	1.422311e-03	1.973337e-03
Pseudomonas_E	1.420060e-03	2.808340e-03
JAGNZR01	1.273646e-03	4.170041e-03
Phocea	1.209038e-03	2.372714e-03
RGIG4140	1.207336e-03	6.396700e-03
Negativibacillus	1.182472e-03	1.519004e-03
WRKB01	1.173050e-03	2.875486e-03
Spyradomonas	1.153313e-03	1.963346e-03
Aminipila	1.114705e-03	2.324044e-03
Romboutsia_A	1.070399e-03	1.851798e-03
Serratia_A	1.045777e-03	3.540183e-03
CAKVBE01	1.027988e-03	3.204532e-03
JAEZVV01	9.378374e-04	2.509149e-03
RGIG8482	9.213532e-04	4.996540e-03
Coprobacter	9.079215e-04	1.527339e-03
RGIG7389	9.070330e-04	1.099182e-03
Massiliimalia	8.310581e-04	1.432050e-03
Shewanella	8.297368e-04	2.690699e-03
UBA7488	8.270131e-04	1.824546e-03
Robinsoniella	7.608379e-04	1.761894e-03
Coprobacillus	7.318328e-04	1.542562e-03
Bacilliculturomica	7.288853e-04	1.183076e-03
Kluyvera	7.218591e-04	3.082164e-03
JAJBUQ01	6.689051e-04	1.230310e-03
IOR16	6.685867e-04	9.975667e-04
UBA1174	6.599272e-04	3.520933e-03
Bradyrhizobium	6.440180e-04	2.407832e-03
HGM16780	6.169676e-04	2.571909e-03
MGBC133411	5.654305e-04	9.653080e-04
Amedibacterium	5.586566e-04	2.772281e-03
Citrobacter	4.794230e-04	1.553079e-03
Anaerotignum	4.725340e-04	1.010493e-03
Muricomes	4.633015e-04	6.762865e-04
Fimivivens	4.584178e-04	6.442620e-04
51-20	3.751337e-04	2.088656e-03
JAGPHI01	3.353114e-04	7.138362e-04
UBA1794	3.283644e-04	5.787967e-04
Yersinia	3.213296e-04	1.133201e-03
Longicatena	3.101858e-04	1.727042e-03
Massilioclostridium	2.871724e-04	6.480957e-04
Cryptoclostridium	2.807538e-04	6.721141e-04
CALXSC01	2.509121e-04	7.682134e-04
Hespellia	2.508300e-04	4.781272e-04
Dysosmobacter	2.451443e-04	4.863795e-04
Scatenecus	2.189717e-04	1.074567e-03
Faecalimonas	2.166638e-04	4.418007e-04
CAZU01	1.870860e-04	1.041651e-03
SIG603	1.481655e-04	2.720693e-04
Lactonifactor	1.397483e-04	5.021416e-04
Enterococcus	1.029579e-04	5.732451e-04
MGBC107952	2.552412e-05	7.936623e-05

genus_arrange <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=sum(relabun)) %>%
    filter(genus != "g__")%>%
    arrange(-mean) %>%
    select(genus) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    pull()

#Per pond
genus_summary %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    mutate(genus=factor(genus, levels=rev(genus_summary_sort %>% pull(genus)))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=genus, group=genus, color=phylum)) +
        scale_color_manual(values=phylum_colors) +
        geom_jitter(alpha=0.5) + 
        facet_grid(.~environment)+
        theme_minimal() + 
        labs(y="Family", x="Relative abundance", color="Phylum")